Monocular Depth Estimation with Sharp Boundary

Monocular depth estimation is the base task in computer vision. Its accuracy has a tremendous improvement in the decade with the development of deep learning. But the boundary blur of the depth map is still a serious problem. Researchers find the boundary blur is mainly caused by two factors. First, the low-level features, containing boundary and structure information, maybe lost in deeper networks during the convolution process. Second, the model ignores the errors introduced by the boundary area due to the few portions of the boundary area in the whole area, during the backpropagation. Focus on the factors mentioned above, two countermeasures are proposed to mitigate the boundary blur problem. Firstly, we design a scene Understanding module and scale transform mod-ule to build a lightweight fuse feature pyramid, which can deal with the low-level feature loss effectively. Secondly, we propose a boundary-aware depth loss function to pay attention to the effects of the boundary's depth value. The extensive experiments show that our method can predict the depth maps with clearer boundaries, and the performance of the depth accuracy based on NYU-depth v2 and SUN RGB-D is competitive.